[PR #1874] [MERGED] Set corret CUDA minimum compute capability version #15980

Closed
opened 2026-04-16 05:13:12 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/1874
Author: @dhiltgen
Created: 1/9/2024
Status: Merged
Merged: 1/9/2024
Merged by: @dhiltgen

Base: mainHead: correct_cuda_min


📝 Commits (1)

  • 1961a81 Set corret CUDA minimum compute capability version

📊 Changes

1 file changed (+2 additions, -2 deletions)

View changed files

📝 gpu/gpu.go (+2 -2)

📄 Description

If you attempt to run the current CUDA build on compute capability 5.2 cards, you'll hit the following failure:
cuBLAS error 15 at ggml-cuda.cu:7956: the requested functionality is not supported


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/1874 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 1/9/2024 **Status:** ✅ Merged **Merged:** 1/9/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `correct_cuda_min` --- ### 📝 Commits (1) - [`1961a81`](https://github.com/ollama/ollama/commit/1961a81f03b474eab428e30e5c9e867548fa9110) Set corret CUDA minimum compute capability version ### 📊 Changes **1 file changed** (+2 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `gpu/gpu.go` (+2 -2) </details> ### 📄 Description If you attempt to run the current CUDA build on compute capability 5.2 cards, you'll hit the following failure: cuBLAS error 15 at ggml-cuda.cu:7956: the requested functionality is not supported --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-16 05:13:12 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#15980